歌单增删歌曲

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare destructiveHint=true and readOnlyHint=false, so '会修改用户账号，调用前请确认' largely repeats that signal. The genuinely additive detail is the ownership constraint (only self-created playlists), which is a permission-like restriction that the annotations do not provide. It does not say what actually gets destroyed — the song is removed from the playlist, not from the library — and it does not mention the 500-item cap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, with the action front-loaded and the scope plus caution trailing. No filler and no repetition beyond the single confirmation reminder.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive mutation with no output schema, the description covers the action and the ownership precondition, which is adequate, but not much more. It leaves open important questions that an agent must resolve before invoking it, as with a destructive tool: whether partial failures are possible in a multi-song batch, and whether removing a song deletes it outright or just detaches it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: op, song_ids and playlist_id all carry inline descriptions, including the add/remove enum values. The description does not add any parameter-level detail (for example, how duplicates are handled or whether song_ids must be unique). Baseline 3 applies when the schema does all the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the specific verb pair (添加/移除) and the resource (歌单歌曲), and adds a meaningful scope restriction: only playlists the current user created. That scope restriction implicitly separates it from create_playlist, get_playlist, and like_song, but no sibling is named explicitly, so the differentiation is only in the description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states one precondition — the playlist must be one the user created — and adds '调用前请确认', implying a confirmation step. Beyond that, it gives no guidance: no alternative for other users' playlists, no note on whether adding an already-present song is a no-op or an error, and nothing about batch-size limits that might make it necessary to split calls.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.